Resume a stopped task run
Pick a stopped run back up in its own conversation instead of repeating it: the transcript is already the agent’s context, so it continues from what it saved rather than redoing the work. Starts a new run that adopts the original’s chat. Pass message to steer the continuation; without it the agent is told to read back over what it did and carry on. 422 run_not_resumable if the run already completed or has no conversation (send it a follow-up instead), 409 run_busy if it or another run of the task is still in progress.
Authorizations
API key in the format: Bearer {api_token}
Headers
Makes this write safe to retry: a repeat with the same key replays the first response instead of creating a second resource. Scoped to the account, remembered for 24 hours; reusing a key with a different payload is an error.
255Path Parameters
Task run id (trun_...)
Body
Optional instructions for the continuation. Defaults to asking the agent to resume from its last saved step.
Response
Accepted — the resumed turn runs in the background on a new run; poll GET /task_runs/{id} or open its stream.
The run's own conversation (aichat_...): what it read, called and said. Read it with search_chats.
pending, running, completed, failed, needs_input, timed_out, unknown, skipped, cancelled When a stop was requested. The run stays running until it reaches its next step, then settles as cancelled.
condition, no_paid_plan_or_credits, no_recent_activity, no_task_activity, no_personal_sources, wake_gate, wake_limit, rate_limited, misfire, task_busy, account_at_capacity, member_credit_cap, agent_archived, null delivered, not_delivered, not_requested, unknown How the agent closed a completed run: verified (it re-checked the result), recorded (it reported without re-checking), or recovered (it never reported; summary is its last message). Null unless an agent turn completed the run.
verified, recorded, recovered, null scheduled, event, manual The event that started this run, {type, data}, exactly as the run received it; data matches the event's webhook payload. Null for a run no event started. POST /task_runs/{id}/replay runs the task again on it.
The run (trun_...) whose event this run replays. Null unless started by POST /task_runs/{id}/replay.
The agent's final reply, once the run settled. Present on single-run responses, not in lists.
The reply parsed and validated against the response_format the run was started with. Null when none was given or it did not validate.
Why the reply did not parse or validate against response_format.

